He gives an example: “Pretend you’re driving and you’re late to a doctor’s appointment. You start whipping through traffic so that you can get there faster. Your sense of self is defined as ‘you contained within the car.’ When you need to get somewhere fast, it’s easy to behave selfishly, but driving is an inherently communal activity that’s pretty high stakes in terms of safety. “So, let’s imagine an upgrade to our understanding of interdependence in that situation,” Duane continues. “What if we had the ability to look not just at our own needs but at all of traffic—all the car deaths, all the people being late, all the people on their way to weddings or to buy food or whatever they’re driving for? Human cognition can’t imagine all the thousands of cars on the road, but AI can! “So, what if AI could do some co-thinking, augment our perception. Make us think more about the illusion of self in the first place, or to call out the subtle conceits of our humanness. There could be a shift of me to we, and I think these technologies can absolutely be part of that. If people throw away technology based on their distaste for it, which is a reasonable thing, they’ll also be leaving this potential on the table.
At a conference in Nepal where CSAS brought together Buddhists and scientists, one scientist asked GPT-3 to write “Four Bodhisattva Vows from the Perspective of a Bioengineer.” GPT-3 complied: *As a bioengineer, I vow to dedicate my life to the welfare of all beings. I will strive to use my knowledge and skills to create new technologies that benefit all. I will strive to be mindful of the potential harms of my work, and to do my best to avoid creating any harm or suffering. I will continually seek to deepen my understanding of bioengineering, so as to better serve humanity and be of benefit to others. I will strive to be an example of ethical conduct, and to embody the virtues of wisdom, compassion, and humility. May my work be a source of healing and joy for all those I encounter.*
There were three things GPT-3 returned to again and again,” explains Thomas. “The first was love, this profound sense that love is at the core of everything. The next was returning to the present moment, being aware of the present moment. The third was the fact that we are connected to everything, to the universe around us and to each other, which is foundational to Buddhism.”
AI is not quite there,” he says. “These systems lack what’s being referred to as second-level context. ChatGPT or something like it doesn’t take the extra step of confirming the things it says. Right now, these chatbots dispense what experts call coherent nonsense. That feels dangerous.”
Note: Mostly, AI can’t tell you anything you don’t already know, it can just reorganize the words you put to what you already know in new ways that may help you understand what you know, better. If it does tell you something new, it comes with the burden of having to validate and verify.
